irmadlad

Shit I deleted my post. Yes I have been enjoying some greenery so you just have to hear me out. I have an old countertop ice maker that stripped it’s gears. The refrigeration loop is fine. Pretty wild how small it is. I was wondering…what if I provisioned some brackets on which to mount a muffin fan of unknown CFM, to blow across the coils thru several sheets of mesh of varying gauges to collect moisture drained off to an unknown location, and duct that indirectly into the computer, like a miniature Liebert server room cooling unit. I worry about the moisture tho. Constructing a desiccant wheel seems improbable. I could reheat the cool air upstream or mix warmer air in with the stream to so the outlet air doesn’t stay at a very low dew point and “rewet” downstream components. Perhaps with a small filament heat coil. HMMmmmmm

Shit I deleted my post. Yes I have been enjoying some greenery so you just have to hear me out. I have an old countertop ice maker that stripped it’s gears. The refrigeration loop is fine. Pretty wild how small it is. I was wondering…what if I provisioned some brackets on which to mount a muffin fan of unknown CFM, to blow across the coils thru several sheets of mesh of varying gauges to collect moisture drained off to an unknown location, and duct that indirectly into the computer, like a miniature Liebert server room cooling unit. I worry about the moisture tho. Constructing a desiccant wheel seems improbable. I could reheat the cool air upstream or mix warmer air in with the stream to keep the so the outlet air doesn’t stay at a very low dew point and “rewet” downstream components. Perhaps with a small filament heat coil. HMMmmmmm

OK, I’ve just been enjoying some flowers, so you must hear me out. I have an old countertop ice maker that the gears stripped out on it, but I saved it thinking, like the man I am, I bet I can repurpose this later on. I was wondering…what if I ripped the gears that push the ice up, provision some brackets to hold a muffin fan of unknown CFM, and bow the cool air, through a fine mesh screen (multiple gauges would probably be needed to create a moisture collector drained off to an unknown location) to collect the moisture, through a ‘U’ tube of unknown construction, drill a small in the center of the ‘U’ to let any other other moisture bleed. Then duct that to the computer. Much like a miniature Liebert unit cools a server room.

I worry about the moisture. Liebert units have built in de-humidification measures and they vary from model to model. Building a miniature deseccant wheel seems improbable. Hmmmmm I could reheat the air slightly or mix with warmer air so the outlet air doesn’t stay at a very low dew point and “rewet” downstream components

Sweet.

I pay around $8/month USD. Now, there are factors involved. One, electricity in my locale is relatively cheap. In addition, I have solar. To contrast the Optiplex 7020 SFF, I used run the same containers/content on a Dell T320. It cost $40/month USD. which still isn’t an outrageous expenditure for someone with another type of hobby. Some of my other hobbies, like creating music, those prices climb steeply, rapidly. Last count I have 48 guitars, several banjos, 8 bass, an oud, mandolin, 4 full size Korg synth keyboards. three violins, and amps out the yang. So $40/month was peanuts, but I wanted something that wasn’t such a hog. Plus the heat dissipated by the T320 was significant, and that is passed on to your AC bill as well. The 7020 is much quieter, energy efficient, and produces very little heat. Win, win.

Hybrid (CPU + GPU) inference is where it’s at these days. It opens up a whole world of huge MoE models, whereas on an 5090 you are stuck with Qwen 27B.

Why you do this to me? LOL Injecting your options. But seriously thank you for the advice. I’m really green in the AI arena. So I’m trying to feel my way around, trying not to spend money on equipment I’ll regret later.

Be aware that you pay a significant performance penalty for going over occulink.

And that’s why it’s tentative. The reason I’m leaning towards the dock is that, while the 5090 will fit, physically in the case, I am worried about heat dissipation. Even now, when I fire up a moderate model and run it through some paces, I can see the temps rising fairly quickly. So, if I’m going to drop that kind of cabbage on a 5090, the one thing I don’t want to do is watch it turn into a shrink-i-dink.

LOL Not quite, however, I am choking on the 5090 but as I understand, that’s the better option, and 32 GB seems to be the sweetspot for AI. I actually picked up the tower and original RAM for less than $500 USD.

Deepseek V4 flash

What are the advantages of Deepseek V4 flash?

[AIT] Well, let’s see…nothing really new on the server. Still waiting for something interesting besides *.arr. I did provision a new tower with the following specs:

• CPU: Ryzen 5 5600X
• GPU: ASUS ROG RX 580
• RAM: Came with 32 GB Corsair Vengeance RGB DDR4 / dropped another 96 GB in it.
• SSD: WD Black NVMe M.2 iirc it’s about a 1tb
• Asus motherboard
• Working on acquiring a GeForce RTX 5090 32GB GDDR7 mounted on a OCuLink external dock (tentative - may change)

This, obviously, will be an local AI machine

Your server looks fabulous, and I’m not discouraging you from pursuing it in the least. However, if I may draw from my own personal experience and what I am currently running, it may give you some ideas. Currently, I am running 53 containers on a Optiplex 7020 SFF with the i7-4790 and 32 GB RAM. Just checked and it’s load average at this moment is: 0.47, 0.60, 0.73. Meaning it’s pretty much in an idle state except for logging in just now. Grand total cost was less than $200. It consumes about $8 USD/month.

Unless you’re going to get into selfhosting heavy AI models, most stock PC, office discards, etc built in the last 10 years will do just fine for a homelab, with a little love like some additional RAM or a dual nic card. Immich and Nextcloud will probably require a bit more than 16 GB RAM running together. I don’t run Immich, but I do run Nextcloud and it does just fine with the above set up. No lags, stutters, etc.

This one? That’s a pretty nice look to it.

I mean…I just don’t understand the disconnect. Dev toils and sweats over a app. Dev gives it away for free as opensource. User: @#$%@$$# <insert foot stomping and pouty lip> Fuck that noise.

Audiomuse-AI looks interesting imo

If you decide to deploy Navidrome, there is an Audiomuse-AI plugin for it as well.

I fully disagree with your comment. Frankly your attitude sucks. I will not bother any more attempting to help, rest assured. You missed an opportunity to improve your documentation, on this page:

See, this is why I’d never publish an app. I have long since lost my patience.

What this thread has showed me is that I’m over here playing tiddlywinks.

And the award goes too… Respect my brother!

Honeygain

I’m a bit skeptical. How does that work and how long have you been using it. Have you noticed any weird noise on your firewall?

Is there a down vote bot loose on Lemmy? Weirdness.

Hey bro, forgot to come back and thank you. That worked. I appreciate it greatly.

I really like those big cases. Lots of room for expansion and cooling I’ve got an old CoolerMaster Cosmos II.

spoiler

I took the bottom rails and retrofitted casters on it. It’s huge and hard to move around. Stands about 30" tall.